Coding Assistants

It is an open-source agent harness that treats every component as a plugin, built on an academic framework called Cordis.

Archify is an agent skill that turns plain-English system descriptions into polished, self-contained HTML diagrams you can theme, export, and paste into Slack.

A ruleset that treats every line of generated code as an admission of defeat.

A skill that forces your coding agent to lead with the fix, number the steps, and skip the ceremonial sign-offs.

Composable prompt recipes that force coding agents to align, test, and architect instead of blindly generating code.

ECC exists because raw agent harnesses lack persistent memory, token discipline, and security guardrails, so it layers reusable skills, session hooks, and audit rules on top of them.

Graphify builds a queryable knowledge graph from your whole project so AI assistants can answer architecture questions without grepping raw files.

Orca gives every CLI coding agent its own git worktree so you can run Claude, Codex, and Grok in parallel without stashing or branch juggling.

It strips the telltale signs of AI-generated writing from text, replacing statistical blandness with prose that sounds like it came from a person.

HyperFrames turns HTML, CSS, and seekable animations into deterministic MP4s, built for agents and developers who'd rather skip React and proprietary timelines.

Because verbose AI explanations waste tokens and patience, this skill makes agents talk like cavemen—terse, accurate, and cheap.

OmniRoute keeps your coding agents online by automatically failing over across 177 AI providers—including free tiers—when quotas run dry.

It forces your AI coding agent to ask what you're building, write a plan, and get sign-off before it writes a single line of code.

It gives your terminal an AI pair programmer that can either build freely or explore cautiously without touching your files.

Pi bundles a unified LLM API, agent runtime, and interactive coding CLI into a monorepo that treats every dependency update as a potential attack.

It packages marketing playbooks into markdown skills that turn AI coding agents into growth collaborators for founders and technical marketers.

A terminal multiplexer that tracks whether your coding agents are blocked, working, or done—without leaving the shell.

video-use turns Claude Code into a video editor by making it read transcripts and spot-check visual composites instead of ingesting thousands of raw frames.

One markdown file distills Andrej Karpathy's critique of LLM coding failures into guardrails for Claude and Cursor.

It gives AI coding assistants a structured taste filter, mapping vague project descriptions to industry-specific colors, fonts, and anti-patterns.